We use network analysis and mathematical modeling to understand and quantify the structure, dynamics, and function of biological communities, including their responses to environmental changes such as species extinctions, invasions, climate change, and fisheries. This research program has contributed a more mechanistic understanding of the structure and dynamics of ecological networks, a better integration between theoretical and empirical research in network ecology, and a more predictive theory to evaluate the responses of entire biological communities to environmental change.
News & Events
Interpreting random forest analysis of ecological models to move from prediction to explanation
Simon, S., Glaum, P., Valdovinos, F.S.; (2023); Scientific Reports
"As modeling tools and approaches become more advanced, ecological models are becoming more complex. Traditional sensitivity analyses can struggle to identify the nonlinearities and interactions emergent from such complexity, especially across broad swaths of parameter space. This limits understanding of the ecological mechanisms underlying model behavior. Machine learning approaches are a potential answer to this issue, given their predictive ability when applied to complex large datasets. While perceptions that machine learning is a “black box” linger, we seek to illuminate its interpretive potential in ecological modeling. To do so, we detail our process of applying random forests to complex model dynamics to produce both high predictive accuracy and elucidate the ecological mechanisms driving our predictions. Specifically, we employ an empirically rooted ontogenetically stage-structured consumer-resource simulation model."
Figure 1) Simulation model overview